On the robustness of average losses for partial-label learning
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL). In PLL, identification-based strategy (IBS) purifies each PL on the fly to select the (most likely) TL for training; average-based strategy (ABS) treats all can...
Saved in:
Main Authors: | Lv, Jiaqi, Liu, Biao, Feng, Lei, Xu, Ning, Xu, Miao, An, Bo, Niu, Gang, Geng, Xin, Sugiyama, Masashi |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Article |
語言: | English |
出版: |
2023
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/172190 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Fashion parsing with weak color-category labels
由: Liu, S., et al.
出版: (2014) -
Local-driven semi-supervised learning with multi-label
由: Li, T., et al.
出版: (2014) -
Variants of Partial Learning in Inductive Inference
由: GAO ZIYUAN
出版: (2012) -
Using Under-Trained Deep Ensembles to Learn under Extreme Label Noise: A Case Study for Sleep Apnea Detection
由: Nikolaidis, Konstantinos, et al.
出版: (2022) -
CHALLENGES OF LEARNING UNDER DIFFERENT LEVELS OF SUPERVISION FOR IMAGES AND VIDEOS
由: RAHUL RAHAMAN
出版: (2023)